University of Pittsburgh School of Medicine, United States

Title : Fusion genes detection enhances clinical outcome prediction of hepatocellular carcinoma through machine learning analyses

Abstract:

Hepatocellular carcinoma is one of the most lethal malignancies for humans. Assessing the clinical outcomes of HCC remains challenging. In this study, a panel of 20 fusion genes in 200 hepatocellular carcinoma (HCC) samples was analyzed to predict the recurrence and survival rates of HCC patients undergoing surgical interventions using machine learning models. The results showed that fusion genes, Milan criteria, serum α-fetal protein (AFP), and pathology grade had moderate predictive accuracy for HCC recurrence. However, the combination of selected fusion genes with these clinical parameters significantly enhanced the prediction accuracy of each parameter. When models of fusion genes were applied to predict the 3-year survival rate of HCC patients, they yielded a prediction accuracy of 72.4% in both the training and the testing cohorts. These results outperformed those from the Milan criteria (61.2% training and 58.8% testing), pathology grade (50% training and 49% testing), and serum AFP (66.3% training and 70.2% testing). The combination of a fusion gene panel with Milan criteria, pathology grade, or serum AFP yielded significantly improved results compared to those produced by these clinical parameters alone. As a result, examining the fusion gene status of HCC samples may hold promise as a new and improved approach to assessing the clinical outcomes of this disease.

Biography:

Dr. Luo has been studying molecular mechanisms of human malignancies in the last 35 years. Currently, he is a Professor of Pathology and Director of High Throughput Genome Center at University of Pittsburgh. In the last 29 years, Dr. Luo has been largely focusing on the genetic and molecular mechanism of human cancers such as prostate cancer. He is one of the pioneers in utilizing high throughput gene expression and genome analyses to analyze field effects in prostate cancer and liver cancer. He is also the first in using methylation array and whole genome methylation sequencing to analyze prostate cancer. He and his colleague helped to develop an ultra-low error synthetic long-read sequencing technology called LOOPSeq that can be utilized to quantify mRNA isoforms and mutation isoform distributions in single cell level. His group has discovered 21 novel fusion genes in prostate, liver and colon cancers. Subsequently, his group discovered that many of these fusion genes are recurrent in many other types of human cancers. His group also developed a genome intervention strategy targeting at the chromosomal breakpoint of fusion gene to treat cancers. Overall, these findings advance our understanding of how cancer develops and behaves, and lay down the foundation for better future diagnosis and treatment for human malignancies.